Anshul Mittal

Anshul Mittal

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 May 2020 in Frontiers in Blockchain
Verified
Journal Article
Open access
PDF file
AMAnshul Mittal
Anshul Mittal
SASwati Aggarwal
Swati Aggarwal
Hyperparameters are pivotal for machine learning models. The success of efficient calibration, often surpasses the results obtained by devising new approaches. Traditionally, human intervention is required to tune the models, however, this obtuse outlook restricts the proficiency and competence. Automating this crucial characteristic of learning sustainably, proffers a significant boost in performance and cost optimization. Blockchain technology has revolutionized industries utilizing its Proof-of-Work algorithms for consensus. This complicated solution generates a lot of useless computations across the nodes attached to the network and thus, fritters away a huge amount of precious energy. In this paper, we propose to exploit these inane computations for training deep learning models instead of calculating purposeless hash values, thus, suggesting a new consensus schema. This work distinguishes itself from other related works by capitalizing on the parallel processing prospects it generates for hyperparameter tuning of complex deep learning models. We address this aspect through the framework of Bayesian optimization which is an effective methodology for the global optimization of functions with expensive evaluations. We call our work, Proof of Deep Learning with Hyperparameter Optimization (PoDLwHO).


1 April 2016
Verified
Conference Paper
Closed access
CPChandra Prakash
Chandra Prakash
AMAnshul Mittal
Anshul Mittal
STShubam Tripathi
Shubam Tripathi
RKRajesh Kumar
Rajesh Kumar
NMNamita Mittal
Namita Mittal
Gait analysis applications are not only limited to medical, rehabilitation and sports, but it can also play a decisive role in security and surveillance as a behavioral biometric factor. Gait recognition is non-invasive and doesn't need any cooperation from subject in case of video surveillance. This paper presents a framework for human recognition based on gait without using markers or sensors using multimodel approach. The experiment presented in this paper was initially performed on 10 subjects, whose data were recorded at Raman Lab, MNIT Jaipur. In order to cross validate our approach, we have also used a standard gait database CASIA B.

24 July 2024 in AI
Verified
Journal Article
Open access
PDF file
SASwati Aggarwal
Swati Aggarwal
AMAnshul Mittal
Anshul Mittal
SASanchit Aggarwal
Sanchit Aggarwal
Anshul SinghAnshul Singh
Anshul Singh
Recent studies have exposed the vulnerabilities of deep neural networks to some carefully perturbed input data. We propose a novel untargeted white box adversarial attack, the dynamic programming-based sub-pixel score method (SPSM) attack (DPSPSM), which is a variation of the traditional gradient-based white box adversarial approach that is limited by a fixed hamming distance using a dynamic programming-based structure. It is stimulated using a pixel score metric technique, the SPSM, which is introduced in this paper. In contrast to the conventional gradient-based adversarial attacks, which alter entire images almost imperceptibly, the DPSPSM is swift and offers the robustness of manipulating only a small number of input pixels. The presented algorithm quantizes the gradient update with a score generated for each pixel, incorporating contributions from each channel. The results show that the DPSPSM deceives the model with a success rate of 30.45% in the CIFAR-10 test set and 29.30% in the CIFAR-100 test set.

13 June 2014
Verified
Conference Paper
Closed access
KSKidambi Sreenivas
Kidambi Sreenivas
AMAnshul Mittal
Anshul Mittal
LHLevi Hereth
Levi Hereth
LTLafayette K. Taylor
Lafayette K. Taylor
CHChristopher B. Hilbert
Christopher B. Hilbert